kureha295/deepseek-ai-DeepSeek-R1-Distill-Llama-8B-ortho-baseline-layer-11

Orthogonalized Baseline Model (Layer 11)

This model is an orthogonalized version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B.

Model Details

• Base Model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
• Model Type: Baseline
• Orthogonalization Layer: 11

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("kureha295/deepseek-ai-DeepSeek-R1-Distill-Llama-8B-ortho-baseline-layer-11")
tokenizer = AutoTokenizer.from_pretrained("kureha295/deepseek-ai-DeepSeek-R1-Distill-Llama-8B-ortho-baseline-layer-11")

Citation

If you use this model, please cite the original model and the orthogonalization method used.